Requests 惟一的一個非轉基因的 Python HTTP 庫,人類能夠安全享用。html
警告:非專業使用其餘 HTTP 庫會致使危險的反作用,包括:安全缺陷症、冗餘代碼症、從新發明輪子症、啃文檔症、抑鬱、頭疼、甚至死亡。python
需求:爬取搜狗指定詞條搜索後的頁面數據web
import requests import os #指定搜索關鍵字 word = input('enter a word you want to search:') #自定義請求頭信息 headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36', } #指定url url = 'https://www.sogou.com/web' #封裝get請求參數 prams = { 'query':word, 'ie':'utf-8' } #發起請求 response = requests.get(url=url,params=param) #獲取響應數據 page_text = response.text with open('./sougou.html','w',encoding='utf-8') as fp: fp.write(page_text)
需求:登陸豆瓣電影,爬取登陸成功後的頁面數據ajax
import requests import os url = 'https://accounts.douban.com/login' #封裝請求參數 data = { "source": "movie", "redir": "https://movie.douban.com/", "form_email": "15027900535", "form_password": "bobo@15027900535", "login": "登陸", } #自定義請求頭信息 headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36', } response = requests.post(url=url,data=data) page_text = response.text with open('./douban111.html','w',encoding='utf-8') as fp: fp.write(page_text)
需求:爬取豆瓣電影分類排行榜 https://movie.douban.com/中的電影詳情數據json
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests import urllib.request if __name__ == "__main__": #指定ajax-get請求的url(經過抓包進行獲取) url = 'https://movie.douban.com/j/chart/top_list?' #定製請求頭信息,相關的頭信息必須封裝在字典結構中 headers = { #定製請求頭中的User-Agent參數,固然也能夠定製請求頭中其餘的參數 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36', } #定製get請求攜帶的參數(從抓包工具中獲取) param = { 'type':'5', 'interval_id':'100:90', 'action':'', 'start':'0', 'limit':'20' } #發起get請求,獲取響應對象 response = requests.get(url=url,headers=headers,params=param) #獲取響應內容:響應內容爲json串 print(response.text)
需求:爬取肯德基餐廳查詢http://www.kfc.com.cn/kfccda/index.aspx中指定地點的餐廳數據瀏覽器
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests import urllib.request if __name__ == "__main__": #指定ajax-post請求的url(經過抓包進行獲取) url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword' #定製請求頭信息,相關的頭信息必須封裝在字典結構中 headers = { #定製請求頭中的User-Agent參數,固然也能夠定製請求頭中其餘的參數 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36', } #定製post請求攜帶的參數(從抓包工具中獲取) data = { 'cname':'', 'pid':'', 'keyword':'北京', 'pageIndex': '1', 'pageSize': '10' } #發起post請求,獲取響應對象 response = requests.get(url=url,headers=headers,data=data) #獲取響應內容:響應內容爲json串 print(response.text)
需求:爬取國家藥品監督管理總局中基於中華人民共和國化妝品生產許可證相關數據安全
import requests from fake_useragent import UserAgent ua = UserAgent(use_cache_server=False,verify_ssl=False).random headers = { 'User-Agent':ua } url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList' pageNum = 3 for page in range(3,5): data = { 'on': 'true', 'page': str(page), 'pageSize': '15', 'productName':'', 'conditionType': '1', 'applyname':'', 'applysn':'' } json_text = requests.post(url=url,data=data,headers=headers).json() all_id_list = [] for dict in json_text['list']: id = dict['ID']#用於二級頁面數據獲取 #下列詳情信息能夠在二級頁面中獲取 # name = dict['EPS_NAME'] # product = dict['PRODUCT_SN'] # man_name = dict['QF_MANAGER_NAME'] # d1 = dict['XC_DATE'] # d2 = dict['XK_DATE'] all_id_list.append(id) #該url是一個ajax的post請求 post_url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById' for id in all_id_list: post_data = { 'id':id } response = requests.post(url=post_url,data=post_data,headers=headers) #該請求響應回來的數據有兩個,一個是基於text,一個是基於json的,因此能夠根據content-type,來獲取指定的響應數據 if response.headers['Content-Type'] == 'application/json;charset=UTF-8': #print(response.json()) #進行json解析 json_text = response.json() print(json_text['businessPerson'])